# com.ascent-partners/opencode-workbench (npm · @simonmak-ascent/opencode-workbench)

Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `opencode-workbench.simonmak.com`: 67/100, [markdown](https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/opencode-workbench.md), [page](https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/opencode-workbench)
- npm · `@simonmak-ascent/opencode-workbench`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench.md), [page](https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench)

## Channel facts

- Registry: `npm`
- Package: `@simonmak-ascent/opencode-workbench`
- Version: `4.0.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2267 tokens (~226/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the com.ascent-partners/opencode-workbench MCP server?

com.ascent-partners/opencode-workbench runs locally as an npm package, launched with npx -y @simonmak-ascent/opencode-workbench. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-ascent-partners-opencode-workbench -- npx -y @simonmak-ascent/opencode-workbench
```

### Cursor

```json
{
  "mcpServers": {
    "com-ascent-partners-opencode-workbench": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ascent-partners-opencode-workbench": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-ascent-partners-opencode-workbench -- npx -y @simonmak-ascent/opencode-workbench
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-ascent-partners-opencode-workbench": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-ascent-partners-opencode-workbench --command npx --arg -y --arg @simonmak-ascent/opencode-workbench
```

### Hermes

```yaml
mcp_servers:
  com-ascent-partners-opencode-workbench:
    command: "npx"
    args: ["-y", "@simonmak-ascent/opencode-workbench"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-ascent-partners-opencode-workbench": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ascent-partners-opencode-workbench -t stdio -c npx -a -y @simonmak-ascent/opencode-workbench
```

### Other

```json
{
  "mcpServers": {
    "com-ascent-partners-opencode-workbench": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 69, +30)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Destructive annotations: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail

### 2026-10-14 (score 39)

First indexed and scored.

## MCP tools (10)

### `describe_workbench` (~96 tokens)

Workbench server info

Describe this MCP server from its bundled profile without contacting any target or making a network call: repository URL, the default component set, components grouped by tier (required/core/optional), and optional MCP add-ons. It takes no parameters, is always safe, and returns instantly. Use it first to resolve a component id for install_component/remove_component/update_component or to see available add-ons; use inspect_target for a machine's live state.

Output parameters:

- `components` (array): Every component with id, tier and description.
- `defaultComponents` (array): Component ids installed by default.
- `optionalMcp` (array): Optional MCP add-on ids available in the profile.
- `packageRoot` (string): Filesystem path of the installed package.
- `repo` (string): Web URL of the workbench repository.
- `repoGit` (string): Git clone URL of the workbench repository.

### `inspect_target` (~224 tokens)

Inspect a Linux target

Probe one Linux machine — this host (`local`) or a remote host over SSH (`ssh`) — and report its OS, kernel, architecture, package manager, Node/npm, OpenCode, Docker, and per-tool detection flags, plus the names (never values) of credentials present. Read-only: it runs one shell probe as the target user (over SSH when `mode:ssh`), installs nothing, writes nothing, contacts no external service, and can take a few seconds per hop. Parameter semantics: `target.mode` selects local vs ssh (default `local`); `target.host` is required only for ssh; `target.user` defaults to the ssh config/current user; `target.cwd` sets the directory for relative checks; `target.port`/`identityFile` pass straight to ssh. Use it to see what a clone would touch, then plan_clone to turn that into an ordered plan and apply_clone to perform it.

Input parameters:

- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).

Output parameters:

- `arch` (string): CPU architecture (e.g. x86_64, aarch64).
- `configDir` (string): OpenCode config directory on the target.
- `dockerRunning` (boolean): Whether the Docker daemon is reachable.
- `envPresent` (string): Space-separated names of credentials present on the target (values are never read).
- `has` (object): Detection flags for git, curl, node, npm, corepack, pnpm, docker, uv, gh, opencode, sudo.
- `home` (string): Home directory on the target.
- `kernel` (string): Kernel name and release.
- `nodeVersion` (string): Installed Node.js version, if any.
- `npmModules` (string): npm global modules directory.
- `opencodeBin` (string): Path to the opencode binary, if installed.
- `osId` (string): OS identifier (e.g. ubuntu, debian, rhel).
- `osName` (string): Human-readable OS name.
- `osVersion` (string): OS version string.
- `packageManager` (string): Detected package manager (apt-get, dnf, yum, apk, pacman, zypper, or none).
- `user` (string): Detected user on the target.
- `workspaceDefault` (string): Default directory where the profile repo will be cloned.

### `plan_clone` (~232 tokens)

Plan a Workbench clone

Return a read-only plan for a target: compare it against the Workbench profile and list each component as `install`, `present`, or `manual`, with the commands that would run. It still runs a detection probe on the target (same access as inspect_target) but clones nothing and writes nothing. Parameter semantics: `components` restricts the diff to those ids (default: required+core); `workspace` sets the expected profile path on the target (default `~/opencode-workbench`); `profileUrl` overrides the git remote. Use it to preview before apply_clone, which performs the changes.

Input parameters:

- `components` (array): Component ids to include; defaults to required+core.
- `dryRun` (boolean): Report only; make no changes.
- `profileUrl` (string): Override profile git URL.
- `skipRepo` (boolean): Do not clone/update the profile repo on the target.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Target directory for the profile repo.

Output parameters:

- `inspect` (object): Full inspection of the target.
- `steps` (array): Per-component plan.
- `target` (string): Label of the inspected target.
- `toInstall` (array): Component ids that will be installed.

### `apply_clone` (~320 tokens)

Apply a Workbench clone

Apply the Workbench profile to a target: clone the repo and install missing components (OpenCode CLI, Node/pnpm, MCP servers, skills, plugins, optional Docker). It OVERWRITES `<home>/.config/opencode/opencode.json`, copies `AGENTS.md`, resets an existing profile repo to `origin/main`, and runs global installs that need write permission (plus SSH for `mode:ssh`) and can take minutes. Writes a names-only `~/.env.workbench` (mode 600); never secret values. Consent-gated and idempotent: without `confirm:true` it returns the plan and changes nothing. Parameter semantics: `components` defaults to required+core; `workspace` defaults to `~/opencode-workbench`; `skipRepo` skips the clone/update; `profileUrl` overrides the git remote; `dryRun` returns the plan. To preview only, use plan_clone.

Input parameters:

- `components` (array): Component ids to include; defaults to required+core.
- `confirm` (boolean): Set true to actually install. When absent, the call returns a plan and makes no changes.
- `dryRun` (boolean): Report only; make no changes.
- `profileUrl` (string): Override profile git URL.
- `skipRepo` (boolean): Do not clone/update the profile repo on the target.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Target directory for the profile repo.

Output parameters:

- `configPath` (string): Path of the written opencode.json.
- `degraded` (array): Capabilities disabled because required credentials are absent; fill the named env vars to enable them.
- `dryRun` (boolean): True when the run made no changes.
- `envPath` (string): Path of the written ~/.env.workbench template.
- `envVars` (array): Environment variable names listed in the env template.
- `installed` (array): Components installed, with exit codes and output.
- `model` (string): Default model selected for the target (DeepSeek when its key is present, else the OpenCode Zen free floor).
- `plan` (object): Presented when confirmation is required.
- `providerMode` (string): Which provider the model resolves to.
- `requiresConfirmation` (boolean): True when the call returned a plan without applying; re-call with confirm:true to install.
- `skipped` (array): Component ids skipped (already present or manual).
- `target` (string): Label of the target.
- `workspace` (string): Directory where the profile repo was cloned.

### `verify_clone` (~258 tokens)

Verify a Workbench clone

Re-check a target after a clone: return a per-component `present`/`missing` list plus whether `opencode.json` and `~/.env.workbench` exist. Read-only and idempotent: it runs a detection probe (SSH or local) and checks files, writing nothing. `target` selects the machine (`local` or SSH) and its `home` is where the `opencode.json` and `~/.env.workbench` checks run; `components` restricts the check to those ids (omit it to check every component, the default); `workspace` sets the profile path used by component checks. Use it after apply_clone and after component changes; for a pre-clone preview use plan_clone.

Input parameters:

- `components` (array): Component ids to include; defaults to required+core.
- `dryRun` (boolean): Report only; make no changes.
- `profileUrl` (string): Override profile git URL.
- `skipRepo` (boolean): Do not clone/update the profile repo on the target.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Target directory for the profile repo.

Output parameters:

- `components` (array): Per-component presence detection.
- `configExists` (boolean): Whether opencode.json exists on the target.
- `envExists` (boolean): Whether ~/.env.workbench exists on the target.
- `missing` (array): Component ids detected as missing.
- `target` (string): Label of the target.

### `install_component` (~237 tokens)

Install one Workbench component

Install a single Workbench component by id (e.g. `node`, `opencode`, `npm-mcps`, `skills`) on a target; `component` must be an id from describe_workbench. Overwrites that component's files when present (e.g. `skills`/`plugins` replace the copies under `<home>/.config/opencode`); global installs need write permission and can take minutes. Idempotent and consent-gated: without `confirm:true` it returns the plan. Parameter semantics: `component` is required; `workspace` defaults to `~/opencode-workbench`; `confirm` defaults to false (plan only). Use it for one targeted component; use apply_clone to install the full default set.

Input parameters:

- `component` (string, required): Component id from describe_workbench.
- `confirm` (boolean): Set true to actually install. When absent, the call returns a plan and makes no changes.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Target directory for the profile repo.

Output parameters:

- `configPath` (string): Path of the written opencode.json.
- `degraded` (array): Capabilities disabled because required credentials are absent; fill the named env vars to enable them.
- `dryRun` (boolean): True when the run made no changes.
- `envPath` (string): Path of the written ~/.env.workbench template.
- `envVars` (array): Environment variable names listed in the env template.
- `installed` (array): Components installed, with exit codes and output.
- `model` (string): Default model selected for the target (DeepSeek when its key is present, else the OpenCode Zen free floor).
- `plan` (object): Presented when confirmation is required.
- `providerMode` (string): Which provider the model resolves to.
- `requiresConfirmation` (boolean): True when the call returned a plan without applying; re-call with confirm:true to install.
- `skipped` (array): Component ids skipped (already present or manual).
- `target` (string): Label of the target.
- `workspace` (string): Directory where the profile repo was cloned.

### `remove_component` (~285 tokens)

Remove one Workbench component

Uninstall one Workbench component by id from a target — the inverse of install_component — for a bounded, documented subset with an automated uninstall (e.g. `opencode`, `pnpm`, `npm-mcps`, `skills`, `docker-containers`); `component` must be an id from describe_workbench. Idempotent: an already-absent component reports `absent`; a component with no automated uninstall (system packages such as git/curl/node) reports `manual`. Destructive and consent-gated: without `confirm:true` it returns a preview and changes nothing, and it deletes only that component's files — never `opencode.json` or the profile repo. Parameter semantics: `workspace` sets the profile path some removals need; `dryRun` reports without changing. Use it to tear down one component; for several, call it per id.

Input parameters:

- `component` (string, required): Component id from describe_workbench.
- `confirm` (boolean): Set true to actually remove. When absent, the call returns a preview and makes no changes.
- `dryRun` (boolean): Report the action without changing anything.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Profile repo directory (used by components whose removal needs it).

Output parameters:

- `action` (string): What happened: removed, updated, already absent, or manual (no automated uninstall).
- `code` (number): Exit code of the action.
- `id` (string): Component id acted on.
- `output` (string): Captured output (truncated).
- `requiresConfirmation` (boolean): True when the call returned a preview without acting; re-call with confirm:true.
- `target` (string): Label of the target.

### `update_component` (~234 tokens)

Update one Workbench component

Update one Workbench component in place by id: re-run its install script to fetch the current version (e.g. `opencode` re-runs the official installer; `npm-mcps` reinstalls the latest globals). It OVERWRITES the component's files, needs write permission, and can take minutes for global installs; the resolved version may change. Parameter semantics: `component` must be an id from describe_workbench; `workspace` defaults to `~/opencode-workbench`; `dryRun` previews; `confirm` defaults to false — set `confirm:true` to apply. For the whole profile use apply_clone.

Input parameters:

- `component` (string, required): Component id from describe_workbench.
- `confirm` (boolean): Set true to actually update. When absent, the call returns a preview and makes no changes.
- `dryRun` (boolean): Report the action without changing anything.
- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `workspace` (string): Profile repo directory (used by components whose update needs it).

Output parameters:

- `action` (string): What happened: removed, updated, already absent, or manual (no automated uninstall).
- `code` (number): Exit code of the action.
- `id` (string): Component id acted on.
- `output` (string): Captured output (truncated).
- `requiresConfirmation` (boolean): True when the call returned a preview without acting; re-call with confirm:true.
- `target` (string): Label of the target.

### `list_required_credentials` (~179 tokens)

List required credentials

List the credentials the profile references, which the target already provides, and how to acquire each missing one. Value-blind: it reads only whether each env var is set — no values, no network, no writes — via one read-only probe. Parameter semantics: `target` selects the machine (`local` or SSH) and its `home` sets the returned `template` path and the env file the presence check reads; there are no other parameters. Returns `present`/`missing` var-name arrays plus one guidance record per credential (`var`, `purpose`, `url`, `method`, `command`). Use it after plan_clone to see what would degrade; act on one credential with run_auth_flow.

Input parameters:

- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).

Output parameters:

- `credentials` (array): Every credential the profile references with its acquisition guidance.
- `missing` (array): Credential names not present.
- `present` (array): Credential names already present on the target.
- `target` (string): Label of the inspected target.
- `template` (string): Path of the env file to fill in.

### `run_auth_flow` (~202 tokens)

Acquire one credential (best-effort)

Return the acquisition plan for one credential on a target: the provider URL, the exact non-interactive command when one exists (e.g. `opencode auth login`, `opencode mcp auth vercel`, `gh auth login`), and whether it is already present. Read-only and value-blind: it emits guidance and re-checks presence with one read-only probe; it does not run the commands or handle secret values. Parameter semantics: `var` must be an env var name returned by list_required_credentials (unknown names error); `target` selects the machine and its `home` is where the value should be written. Use it for a single credential; it does not replace that listing.

Input parameters:

- `target` (object, required): The machine to operate on: this host (local) or a remote host over SSH (ssh).
- `var` (string, required): Credential env var name from list_required_credentials (e.g. OPENCODE_API_KEY).

Output parameters:

- `command` (string): Command for the agent/user to run.
- `method` (string): Acquisition method.
- `next` (string): What to do next.
- `present` (boolean): Whether the credential is present now.
- `target` (string): Label of the target.
- `url` (string): Provider URL to open.
- `var` (string): Credential being acquired.
- `verified` (boolean): True when the credential is present and ready.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench#diagnostics

## Score history

- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 69
- 2026-10-14: 39

## Common questions

### What is the com.ascent-partners/opencode-workbench MCP server?

com.ascent-partners/opencode-workbench is an MCP server listed in the public MCP registry as com.ascent-partners/opencode-workbench. Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH. This page covers its npm package (@simonmak-ascent/opencode-workbench).

### Is the com.ascent-partners/opencode-workbench MCP server safe to use?

com.ascent-partners/opencode-workbench scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the com.ascent-partners/opencode-workbench MCP server expose?

com.ascent-partners/opencode-workbench exposes 10 tools: describe_workbench, inspect_target, plan_clone, apply_clone, verify_clone, and 5 more. Their descriptions and schemas cost roughly 2,267 tokens of context every time the server is loaded.

### Is the com.ascent-partners/opencode-workbench MCP server still maintained?

com.ascent-partners/opencode-workbench is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the com.ascent-partners/opencode-workbench MCP server under?

com.ascent-partners/opencode-workbench declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@simonmak-ascent/opencode-workbench
- Socket report: https://socket.dev/npm/package/@simonmak-ascent/opencode-workbench
- Repository: https://github.com/simonmak-ascent/opencode-workbench
- Changelog RSS feed: https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench.json
- HTML version of this page: https://verifymcp.io/servers/com-ascent-partners-opencode-workbench/simonmak-ascent-opencode-workbench